authorize-release

authorize-release is a skill for Claude Code, Codex from lukasrepublic/agentic-foundry. It costs 71 tokens per session (641 once invoked), scanned A, original, MIT.

A review workflow for approving a release one small work item at a time before implementation starts.

In plain words
What is it for?
Use it to inspect release items, confirm their specifications and acceptance checks, and authorize each item for dispatch.
Why use it?
It keeps each item tied to its own acceptance checklist and prevents an entire release from receiving one unchecked approval.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the foundry plugin — 47 skills, 8 agents, 8 hooks, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/lukasrepublic/agentic-foundry/authorize-release
Any agent
npx skills add lukasrepublic/agentic-foundry --skill authorize-release
Clone the repo
git clone --depth 1 https://github.com/lukasrepublic/agentic-foundry

Made for: Claude Code, Codex.

Or install foundry, the plugin that ships this one along with the rest of its 47 skills, 8 agents, 8 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for authorize-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/authorize-release.svg)](https://agentmods.dev/skills/lukasrepublic/agentic-foundry/authorize-release)
Your own site
<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/authorize-release"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/authorize-release.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.00641
Opus 5 $0.00036 $0.00320
Sonnet 5 $0.00014 $0.00128
Haiku 4.5 $0.00007 $0.00064

Measured 4d ago against content hash cb488fdd4102, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

authorize-release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/authorize-release/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/foundry:authorize-release

A batch review surface over a release's atoms. Ergonomics only — it does NOT introduce an "authorize the release once" shortcut; every atom is authorized per-atom (each carries its own acceptance-contract.yaml + authorized: record, and /foundry:dispatch refuses to dispatch any atom that is not itself in state AUTHORIZED).

When to trigger

  • "authorize release <slug>", "/foundry:authorize-release <slug>" — after the release is DRAFT-shaped (atoms enumerated) and BEFORE implementation dispatch (steel-man-1 ordering).

Procedure

  1. Resolve the release → its ordered atom list, each with a drafted acceptance-contract.yaml. Refuse any atom missing its contract (author it first).
  2. Review precondition. Each atom's spec must have cleared the single-pass /foundry:spec-review (recorded content-bound; the deep opt-in /foundry:audit also satisfies it) or carry the operator skip review; reason: token. Authorization presumes REVIEWED specs.
  3. Batch display. For each atom, show the scope + checkpoints the operator is signing (the per-atom dry-run from foundry-authorize.py without --yes). The operator reviews the whole wave at once.
  4. Per-atom confirm + freeze. On operator confirmation, authorize EACH atom singly:
    python3 "${CLAUDE_PLUGIN_ROOT}/scripts/foundry-authorize.py" \
      --spec <atom-spec> --contract <atom-contract> --operator <op> --mode <regular|lean> --yes
    
    Per-atom granularity is preserved — the operator may authorize a subset, defer others, or mark specific atoms hard. Each freeze records its own authorization-trail entry.
  5. Hand off the authorized atoms to /foundry:mode-autonomous (or per-atom /foundry:dispatch).

Anti-patterns

  • An "authorize the release once" shortcut — there is none; per-atom authorization + per-atom merge re-check is invariant.
  • Authorizing atoms whose contracts skipped the audit without the explicit operator token.
  • Self-confirming the batch — the operator's review of the displayed checkpoints is the authority.
  • On a harness denial during batch authorization, see docs/harness-denial-fallback.md and STOP: hand back the exact denied per-atom invocation; never retry it — resolve it through settings, then resume the batch.

Read the full file on GitHub · 46 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 46 lines · 71 tokens per session scan A cb488fdd4102

Subscribe to this mod's changes

authorize-release is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 641 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.